Merge pull request #27 from AlexandrovLab/development

mdbarnesUCSD · web-flow · commit 0363d17caf93 · 2022-08-03T14:49:32.000-07:00
Development
diff --git a/COSMIC_v3_SBS_GRCh37_noSBS84-85.txt b/COSMIC_v3_SBS_GRCh37_noSBS84-85.txt
@@ -1,4 +1,4 @@
-MutationTypes	SBS1	SBS2	SBS3	SBS4	SBS5	SBS6	SBS7a	SBS7b	SBS7c	SBS7d	SBS8	SBS9	SBS10a	SBS10b	SBS11	SBS12	SBS13	SBS14	SBS15	SBS16	SBS17a	SBS17b	SBS18	SBS19	SBS20	SBS21	SBS22	SBS23	SBS24	SBS25	SBS26	SBS27	SBS28	SBS29	SBS30	SBS31	SBS32	SBS33	SBS34	SBS35	SBS36	SBS37	SBS38	SBS39	SBS40	SBS41	SBS42	SBS43	SBS44	SBS45	SBS46	SBS47	SBS48	SBS49	SBS50	SBS51	SBS52	SBS53	SBS54	SBS55	SBS56	SBS57	SBS58	SBS59	SBS60
+MutationType	SBS1	SBS2	SBS3	SBS4	SBS5	SBS6	SBS7a	SBS7b	SBS7c	SBS7d	SBS8	SBS9	SBS10a	SBS10b	SBS11	SBS12	SBS13	SBS14	SBS15	SBS16	SBS17a	SBS17b	SBS18	SBS19	SBS20	SBS21	SBS22	SBS23	SBS24	SBS25	SBS26	SBS27	SBS28	SBS29	SBS30	SBS31	SBS32	SBS33	SBS34	SBS35	SBS36	SBS37	SBS38	SBS39	SBS40	SBS41	SBS42	SBS43	SBS44	SBS45	SBS46	SBS47	SBS48	SBS49	SBS50	SBS51	SBS52	SBS53	SBS54	SBS55	SBS56	SBS57	SBS58	SBS59	SBS60
 A[C>A]A	0.000886157	5.80E-07	0.020808323	0.042196498	0.0119976	0.000425233	6.70E-05	0.002329386	0.004830406	4.04E-05	0.044098218	0.000557954	0.00219017	0.000181997	0.000146208	0.004520592	0.00181992	0.001120492	0.000944202	0.015995037	0.002070261	0.000607958	0.051533858	0.001269382	0.000619283	0.000156993	0.006012763	0.000835523	0.0364134	0.009898466	0.000873118	0.005207818	0.000783905	0.063209262	0.001799681	0.009534985	0.022297772	0.00311136	0.00486795	0.008826949	0.025193777	0.003950822	0.012794869	0.011701521	0.028203751	0.002110193	0.001160252	0.029506292	7.68E-18	0.009108136	0.0044	0.067787874	0.000855468	0.025116627	0.119000274	0.140963913	0.015196277	0.00538351	0.002160358	0.005881126	0.012597482	0.012306325	0.058874619	0.003588208	0.006152707
 A[C>A]C	0.002280405	0.000148004	0.016506603	0.033297236	0.009438112	0.000524287	0.000179116	0.000460879	0.001150097	0.000764883	0.047798069	0.004089661	0.001770137	0.006539908	0.000552786	0.001130148	0.000720968	0.01310575	0.000497106	0.0028991	0.000918116	0.000128991	0.015810387	0.000640688	0.001390636	0.002359889	9.54E-05	0.00039925	0.026509756	0.006998915	0.000528071	0.004738015	0.002529694	0.051207503	0.00050591	0.018490274	0.018798122	0.002230975	0.006957071	0.046184034	0.008317945	0.001450302	0.010095952	0.00715093	0.013401782	0.001220112	0.020604479	0.005901258	0.000150038	0.002849417	0.0047	0.029694688	0.00084146	0.007034657	0.127000292	0.001689567	0.006538398	0.001961279	0.000796132	0.002050393	0.015696862	0.001430735	0.006747091	0.002368817	0.000779343
 A[C>A]G	0.000177031	5.23E-05	0.0017507	0.015598705	0.00184963	5.20E-05	7.12E-05	0.000185951	0.000377032	0.000249962	0.004619813	0.000425965	0.000150012	5.35E-05	9.42E-05	0.000540071	0.000263988	0.000413181	4.61E-05	0.001019684	4.76E-05	5.82E-05	0.002431598	0.00024588	2.18E-05	0.000293986	0.000765352	9.86E-08	0.014805448	0.001449775	0.000114015	0.000782672	0.000352957	0.019202814	9.13E-05	0.001659127	0.004459554	0.000414181	5.20E-05	0.00138952	0.002239447	0.001060221	0.001899238	0.002670347	0.002920388	6.14E-05	3.34E-05	0.000626134	9.16E-07	0.00165966	3.00E-04	0.001379753	0.000258141	0.00711471	0.005770013	0.004798772	0.004138986	0.038124854	0.001640271	4.49E-05	0.000205959	0.003331713	0.000824644	0.000141929	2.23E-16
diff --git a/README.md b/README.md
@@ -36,7 +36,7 @@ signature_subgroups = ['remove_MMR_deficiency_signatures',
                        'remove_BER_deficiency_signatures',
                        'remove_Chemotherapy_signatures',
                        'remove_Immunosuppressants_signatures'
-                       'remove_Iatrogenic_signatures'
+                       'remove_Treatment_signatures'
                        'remove_APOBEC_signatures',
                        'remove_Tobacco_signatures',
                        'remove_UV_signatures',
@@ -55,7 +55,7 @@ signature_subgroups = ['remove_MMR_deficiency_signatures',
 |BER_deficiency_signatures|	30, 36|
 |Chemotherapy_signatures|	11, 25, 31, 35, 86, 87, 90|
 |Immunosuppressants_signatures|	32|
-|Iatrogenic_signatures|	11, 25, 31, 32, 35, 86, 87, 90|
+|Treatment_signatures|	11, 25, 31, 32, 35, 86, 87, 90|
 |APOBEC_signatures|	2, 13|
 |Tobacco_signatures	|4, 29, 92|
 |UV_signatures|	7a, 7b, 7c, 7d, 38|
diff --git a/SigProfilerAssignment/data/Examples/Results_scenario_8/SBS96/Suggested_Solution/COSMIC_SBS96_Decomposed_Solution/Activities/Decomposed_Mutation_Probabilities.txt b/SigProfilerAssignment/data/Examples/Results_scenario_8/SBS96/Suggested_Solution/COSMIC_SBS96_Decomposed_Solution/Activities/Decomposed_Mutation_Probabilities.txt
@@ -1,4 +1,4 @@
-Sample Names	MutationTypes	SBS1	SBS3	SBS5	SBS40
+Sample Names	MutationType	SBS1	SBS3	SBS5	SBS40
 SP.Syn.Abst.1	A[C>A]A	0.0	0.3553797487968867	0.09772334441826197	0.5468969067848514
 SP.Syn.Abst.1	A[C>A]C	0.0	0.4556809635442167	0.12426152250268938	0.4200575139530938
 SP.Syn.Abst.1	A[C>A]G	0.0	0.2943048060471408	0.14829235712904196	0.5574028368238172
diff --git a/SigProfilerAssignment/data/Examples/Results_scenario_8/SBS96/Suggested_Solution/COSMIC_SBS96_Decomposed_Solution/Signatures/COSMIC_SBS96_Signatures.txt b/SigProfilerAssignment/data/Examples/Results_scenario_8/SBS96/Suggested_Solution/COSMIC_SBS96_Decomposed_Solution/Signatures/COSMIC_SBS96_Signatures.txt
@@ -1,4 +1,4 @@
-MutationsType	SBS1	SBS3	SBS5	SBS40
+MutationType	SBS1	SBS3	SBS5	SBS40
 A[C>A]A	0.00088616	0.02080832	0.01199760	0.02820375
 A[C>A]C	0.00228040	0.01650660	0.00943811	0.01340178
 A[C>A]G	0.00017703	0.00175070	0.00184963	0.00292039
diff --git a/SigProfilerAssignment/data/Examples/Results_scenario_8/SBS96/Suggested_Solution/SBS96_De-Novo_Solution/Activities/De_Novo_Mutation_Probabilities_refit.txt b/SigProfilerAssignment/data/Examples/Results_scenario_8/SBS96/Suggested_Solution/SBS96_De-Novo_Solution/Activities/De_Novo_Mutation_Probabilities_refit.txt
@@ -1,4 +1,4 @@
-Sample Names	MutationTypes	SBS96A	SBS96B	SBS96C
+Sample Names	MutationType	SBS96A	SBS96B	SBS96C
 SP.Syn.Abst.1	A[C>A]A	0.3447187955321921	0.4818262642019661	0.17345494026584174
 SP.Syn.Abst.1	A[C>A]C	0.46025707870788873	0.35233446831739884	0.18740845297471237
 SP.Syn.Abst.1	A[C>A]G	0.2720194786201318	0.4985789001014602	0.22940162127840788
diff --git a/SigProfilerAssignment/data/Examples/Results_scenario_8/SBS96/Suggested_Solution/SBS96_De-Novo_Solution/Signatures/SBS96_De-Novo_Signatures.txt b/SigProfilerAssignment/data/Examples/Results_scenario_8/SBS96/Suggested_Solution/SBS96_De-Novo_Solution/Signatures/SBS96_De-Novo_Signatures.txt
@@ -1,4 +1,4 @@
-MutationsType	SBS96A	SBS96B	SBS96C
+MutationType	SBS96A	SBS96B	SBS96C
 A[C>A]A	0.02065541	0.02889357	0.01545023
 A[C>A]C	0.01706327	0.01307251	0.01032834
 A[C>A]G	0.00165204	0.00303037	0.00207108
diff --git a/SigProfilerAssignment/data/Examples/Results_scenario_8/SBS96/Suggested_Solution/SBS96_De-Novo_Solution/Signatures/SBS96_De-Novo_Signatures_SEM_Error.txt b/SigProfilerAssignment/data/Examples/Results_scenario_8/SBS96/Suggested_Solution/SBS96_De-Novo_Solution/Signatures/SBS96_De-Novo_Signatures_SEM_Error.txt
@@ -1,4 +1,4 @@
-MutationsType	SBS96A	SBS96B	SBS96C
+MutationType	SBS96A	SBS96B	SBS96C
 A[C>A]A	1.14E-04	9.01E-05	6.00E-04
 A[C>A]C	3.91E-05	5.69E-05	1.11E-04
 A[C>A]G	1.75E-05	1.82E-05	5.49E-05
diff --git a/SigProfilerAssignment/decompose_sub_routines.py b/SigProfilerAssignment/decompose_sub_routines.py
@@ -379,7 +379,7 @@ def signature_decomposition(signatures, mtype, directory, genome_build="GRCh37",
                 # Get the names of the columns for each dataframe
                 denovo_col_names = originalProcessAvg.columns
                 cosmic_col_names = sigDatabases_DF.columns
-                # Get the name for the MutationTypes column
+                # Get the name for the MutationType column
                 cosmic_mut_types_col = cosmic_col_names[0]
                 denovo_mut_types_col =  denovo_col_names[0]
                 # create lists of implemented columns
@@ -675,7 +675,7 @@ def make_final_solution(processAvg, allgenomes, allsigids, layer_directory, m, i
     processAvg= pd.DataFrame(processAvg.astype(float))
     processes = processAvg.set_index(index)
     processes.columns = allsigids
-    processes = processes.rename_axis("MutationsType", axis="columns")
+    processes = processes.rename_axis("MutationType", axis="columns")
     processes.to_csv(layer_directory+"/Signatures"+"/"+solution_prefix+"_"+"Signatures.txt", "\t", float_format='%.8f',index_label=[processes.columns.name]) 
     exposureAvg = pd.DataFrame(exposureAvg.astype(int))
     allsigids = np.array(allsigids)
@@ -881,7 +881,7 @@ def probabilities(W, H, index, allsigids, allcolnames):
         probs.columns = sigs
         col1 = [cols[i]]*len(rows)
         probs.insert(loc=0, column='Sample Names', value=col1)
-        probs.insert(loc=1, column='MutationTypes', value = rows)
+        probs.insert(loc=1, column='MutationType', value = rows)
         if i!=0:
             result = pd.concat([result, probs], axis=0)
         else:
diff --git a/SigProfilerAssignment/decomposition.py b/SigProfilerAssignment/decomposition.py
@@ -97,7 +97,7 @@ def spa_analyze(  samples,  output, signatures=None, signature_database=None,dec
                       'remove_BER_deficiency_signatures' :False,
                       'remove_Chemotherapy_signatures' :False,
                       'remove_Immunosuppressants_signatures' :False,
-                      'remove_Iatrogenic_signatures' :False,
+                      'remove_Treatment_signatures' :False,
                       'remove_APOBEC_signatures' :False,
                       'remove_Tobacco_signatures' :False,
                       'remove_UV_signatures' :False,
@@ -112,7 +112,7 @@ def spa_analyze(  samples,  output, signatures=None, signature_database=None,dec
                       'remove_BER_deficiency_signatures' :['30','36'],
                       'remove_Chemotherapy_signatures' :['11','25','31','35','86','87','90'],
                       'remove_Immunosuppressants_signatures' :['32'],
-                      'remove_Iatrogenic_signatures' :['11','25','31','32','35','86','87','90'],
+                      'remove_Treatment_signatures' :['11','25','31','32','35','86','87','90'],
                       'remove_APOBEC_signatures' :['2','13'],
                       'remove_Tobacco_signatures' :['4','29','92'],
                       'remove_UV_signatures' :['7a','7b','7c','7d','38'],
diff --git a/SigProfilerAssignment/src/FormatFiles/Sample_Files.ID83.all b/SigProfilerAssignment/src/FormatFiles/Sample_Files.ID83.all
@@ -1,4 +1,4 @@
-MutationsType
+MutationType
 1:Del:C:0
 1:Del:C:1
 1:Del:C:2
diff --git a/setup.py b/setup.py
@@ -6,7 +6,7 @@
 if os.path.exists("dist"):
     shutil.rmtree("dist")
 
-VERSION = '0.0.8'
+VERSION = '0.0.9'
 
 
 with open('README.md') as f:
@@ -18,7 +18,7 @@ def write_version_py(filename='SigProfilerAssignment/version.py'):
 # THIS FILE IS GENERATED FROM SigProfilerAssignment SETUP.PY
 short_version = '%(version)s'
 version = '%(version)s'
-Update = '1.Copy number Signatures support 2. Fixed bugs on signature subtypes'
+Update = '1. Make consistent MutationType column 2. Update subgroups'
     
     """
     fh = open(filename, 'w')
@@ -28,9 +28,9 @@ def write_version_py(filename='SigProfilerAssignment/version.py'):
           'scipy>=1.6.3',
           'numpy>=1.21.2',
           'pandas>=1.2.4', 
-          'SigProfilerExtractor>=1.1.7',
-          'SigProfilerMatrixGenerator>=1.1.30', 
-          'sigProfilerPlotting>=1.1.15', 
+          'SigProfilerExtractor>=1.1.9',
+          'SigProfilerMatrixGenerator>=1.2.9', 
+          'sigProfilerPlotting>=1.2.2', 
           'pillow',
           'statsmodels>=0.9.0',
           'scikit-learn>=0.24.2',

Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-MutationTypes SBS1 SBS2 SBS3 SBS4 SBS5 SBS6 SBS7a SBS7b SBS7c SBS7d SBS8 SBS9 SBS10a SBS10b SBS11 SBS12 SBS13 SBS14 SBS15 SBS16 SBS17a SBS17b SBS18 SBS19 SBS20 SBS21 SBS22 SBS23 SBS24 SBS25 SBS26 SBS27 SBS28 SBS29 SBS30 SBS31 SBS32 SBS33 SBS34 SBS35 SBS36 SBS37 SBS38 SBS39 SBS40 SBS41 SBS42 SBS43 SBS44 SBS45 SBS46 SBS47 SBS48 SBS49 SBS50 SBS51 SBS52 SBS53 SBS54 SBS55 SBS56 SBS57 SBS58 SBS59 SBS60`
	`1`	`+MutationType SBS1 SBS2 SBS3 SBS4 SBS5 SBS6 SBS7a SBS7b SBS7c SBS7d SBS8 SBS9 SBS10a SBS10b SBS11 SBS12 SBS13 SBS14 SBS15 SBS16 SBS17a SBS17b SBS18 SBS19 SBS20 SBS21 SBS22 SBS23 SBS24 SBS25 SBS26 SBS27 SBS28 SBS29 SBS30 SBS31 SBS32 SBS33 SBS34 SBS35 SBS36 SBS37 SBS38 SBS39 SBS40 SBS41 SBS42 SBS43 SBS44 SBS45 SBS46 SBS47 SBS48 SBS49 SBS50 SBS51 SBS52 SBS53 SBS54 SBS55 SBS56 SBS57 SBS58 SBS59 SBS60`
`2`	`2`	A[C>A]A 0.000886157 5.80E-07 0.020808323 0.042196498 0.0119976 0.000425233 6.70E-05 0.002329386 0.004830406 4.04E-05 0.044098218 0.000557954 0.00219017 0.000181997 0.000146208 0.004520592 0.00181992 0.001120492 0.000944202 0.015995037 0.002070261 0.000607958 0.051533858 0.001269382 0.000619283 0.000156993 0.006012763 0.000835523 0.0364134 0.009898466 0.000873118 0.005207818 0.000783905 0.063209262 0.001799681 0.009534985 0.022297772 0.00311136 0.00486795 0.008826949 0.025193777 0.003950822 0.012794869 0.011701521 0.028203751 0.002110193 0.001160252 0.029506292 7.68E-18 0.009108136 0.0044 0.067787874 0.000855468 0.025116627 0.119000274 0.140963913 0.015196277 0.00538351 0.002160358 0.005881126 0.012597482 0.012306325 0.058874619 0.003588208 0.006152707
`3`	`3`	A[C>A]C 0.002280405 0.000148004 0.016506603 0.033297236 0.009438112 0.000524287 0.000179116 0.000460879 0.001150097 0.000764883 0.047798069 0.004089661 0.001770137 0.006539908 0.000552786 0.001130148 0.000720968 0.01310575 0.000497106 0.0028991 0.000918116 0.000128991 0.015810387 0.000640688 0.001390636 0.002359889 9.54E-05 0.00039925 0.026509756 0.006998915 0.000528071 0.004738015 0.002529694 0.051207503 0.00050591 0.018490274 0.018798122 0.002230975 0.006957071 0.046184034 0.008317945 0.001450302 0.010095952 0.00715093 0.013401782 0.001220112 0.020604479 0.005901258 0.000150038 0.002849417 0.0047 0.029694688 0.00084146 0.007034657 0.127000292 0.001689567 0.006538398 0.001961279 0.000796132 0.002050393 0.015696862 0.001430735 0.006747091 0.002368817 0.000779343
`4`	`4`	A[C>A]G 0.000177031 5.23E-05 0.0017507 0.015598705 0.00184963 5.20E-05 7.12E-05 0.000185951 0.000377032 0.000249962 0.004619813 0.000425965 0.000150012 5.35E-05 9.42E-05 0.000540071 0.000263988 0.000413181 4.61E-05 0.001019684 4.76E-05 5.82E-05 0.002431598 0.00024588 2.18E-05 0.000293986 0.000765352 9.86E-08 0.014805448 0.001449775 0.000114015 0.000782672 0.000352957 0.019202814 9.13E-05 0.001659127 0.004459554 0.000414181 5.20E-05 0.00138952 0.002239447 0.001060221 0.001899238 0.002670347 0.002920388 6.14E-05 3.34E-05 0.000626134 9.16E-07 0.00165966 3.00E-04 0.001379753 0.000258141 0.00711471 0.005770013 0.004798772 0.004138986 0.038124854 0.001640271 4.49E-05 0.000205959 0.003331713 0.000824644 0.000141929 2.23E-16
Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-Sample Names MutationTypes SBS1 SBS3 SBS5 SBS40`
	`1`	`+Sample Names MutationType SBS1 SBS3 SBS5 SBS40`
`2`	`2`	`SP.Syn.Abst.1 A[C>A]A 0.0 0.3553797487968867 0.09772334441826197 0.5468969067848514`
`3`	`3`	`SP.Syn.Abst.1 A[C>A]C 0.0 0.4556809635442167 0.12426152250268938 0.4200575139530938`
`4`	`4`	`SP.Syn.Abst.1 A[C>A]G 0.0 0.2943048060471408 0.14829235712904196 0.5574028368238172`
Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-MutationsType SBS1 SBS3 SBS5 SBS40`
	`1`	`+MutationType SBS1 SBS3 SBS5 SBS40`
`2`	`2`	`A[C>A]A 0.00088616 0.02080832 0.01199760 0.02820375`
`3`	`3`	`A[C>A]C 0.00228040 0.01650660 0.00943811 0.01340178`
`4`	`4`	`A[C>A]G 0.00017703 0.00175070 0.00184963 0.00292039`
Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-Sample Names MutationTypes SBS96A SBS96B SBS96C`
	`1`	`+Sample Names MutationType SBS96A SBS96B SBS96C`
`2`	`2`	`SP.Syn.Abst.1 A[C>A]A 0.3447187955321921 0.4818262642019661 0.17345494026584174`
`3`	`3`	`SP.Syn.Abst.1 A[C>A]C 0.46025707870788873 0.35233446831739884 0.18740845297471237`
`4`	`4`	`SP.Syn.Abst.1 A[C>A]G 0.2720194786201318 0.4985789001014602 0.22940162127840788`
Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-MutationsType SBS96A SBS96B SBS96C`
	`1`	`+MutationType SBS96A SBS96B SBS96C`
`2`	`2`	`A[C>A]A 0.02065541 0.02889357 0.01545023`
`3`	`3`	`A[C>A]C 0.01706327 0.01307251 0.01032834`
`4`	`4`	`A[C>A]G 0.00165204 0.00303037 0.00207108`
Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-MutationsType`
	`1`	`+MutationType`
`2`	`2`	`1:Del:C:0`
`3`	`3`	`1:Del:C:1`
`4`	`4`	`1:Del:C:2`